GPT for Games: A Scoping Review (2020-2023)

Daijin Yang, Erica Kleinman, Casper Harteveld
4/27/2024
cs.HCcs.AI

No confident code implementation found for this paper.

Abstract

This paper introduces a scoping review of 55 articles to explore GPT's potential for games, offering researchers a comprehensive understanding of the current applications and identifying both emerging trends and unexplored areas. We identify five key applications of GPT in current game research: procedural content generation, mixed-initiative game design, mixed-initiative gameplay, playing games, and game user research. Drawing from insights in each of these application areas, we propose directions for future research in each one. This review aims to lay the groundwork by illustrating the state of the art for innovative GPT applications in games, promising to enrich game development and enhance player experiences with cutting-edge AI innovations.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Games for Artificial Intelligence Research: A Review and Perspectives

85% match1 repo262023

A Controllable Co-Creative Agent for Game System Design

83% match2023

A Survey on Game Playing Agents and Large Models: Methods, Applications, and Challenges

82% match1 repo1622024

The Quest for Content: A Survey of Search-Based Procedural Content Generation for Video Games

82% match2023

GUI Agents for Continual Game Generation

82% match1 repo2026

A Preliminary Study on a Conceptual Game Feature Generation and Recommendation System

82% match2023

Cite this paper

@article{yang2024games,
  title  = {GPT for Games: A Scoping Review (2020-2023)},
  author = {Daijin Yang and Erica Kleinman and Casper Harteveld},
  year   = {2024},
  eprint = {2404.17794},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2404.17794v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2404.17794.svg)](https://codeofpaper.com/paper/2404.17794)

Discussion